Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    0.27
    操作系统
    0.27
    数据
    0.25
    데이터
    0.24
    äne
    0.24
    架构
    0.23
     বছর
    0.23
     огром
    0.23
     મહિના
    0.23
    ruciating
    0.23
    POSITIVE LOGITS
     किंवा
    0.34
     অথবা
    0.32
    或是
    0.30
     अथवा
    0.29
    あるいは
    0.29
     veya
    0.29
    或者是
    0.29
     혹은
    0.29
     alebo
    0.28
     কিংবা
    0.28
    Act Density 0.657%

    No Known Activations